DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations Paper • 2610.29997 • Published 7 days ago • 161
DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents Paper • 2610.19376 • Published 14 days ago • 34
Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training Paper • 2610.28474 • Published 8 days ago • 16
WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State Paper • 2610.28827 • Published 8 days ago • 21
EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience Paper • 2610.26625 • Published 9 days ago • 189
Harnessing Textual Refusal Directions for Multimodal Safety Paper • 2606.31876 • Published 12 days ago • 26
AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments Paper • 2610.25950 • Published 9 days ago • 38
Holi-World: Building Holistic World Intelligence from Human-Ego Experience Paper • 2610.26549 • Published 9 days ago • 173
ComBodied Agents: a New Paradigm of Human-Centric Agentic AI Paper • 2608.10915 • Published Aug 11 • 195